A Stride Toward Wine Yield Estimation from Images: Metrological Validation of Grape Berry Number, Radius, and Volume Estimation

Yield estimation is a key point theme for precision agriculture, especially for small fruits and in-field scenarios. This paper focuses on the metrological validation of a novel deep-learning model that robustly estimates both the number and the radii of grape berries in vineyards using color images...

Full description

Saved in:
Bibliographic Details
Main Authors: Bernardo Lanza, Davide Botturi, Alessandro Gnutti, Matteo Lancini, Cristina Nuzzi, Simone Pasinetti
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/22/7305
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850147116123422720
author Bernardo Lanza
Davide Botturi
Alessandro Gnutti
Matteo Lancini
Cristina Nuzzi
Simone Pasinetti
author_facet Bernardo Lanza
Davide Botturi
Alessandro Gnutti
Matteo Lancini
Cristina Nuzzi
Simone Pasinetti
author_sort Bernardo Lanza
collection DOAJ
description Yield estimation is a key point theme for precision agriculture, especially for small fruits and in-field scenarios. This paper focuses on the metrological validation of a novel deep-learning model that robustly estimates both the number and the radii of grape berries in vineyards using color images, allowing the computation of the visible (and total) volume of grape clusters, which is necessary to reach the ultimate goal of estimating yield production. The proposed algorithm is validated by analyzing its performance on a custom dataset. The number of berries, their mean radius, and the grape cluster volume are converted to millimeters and compared to reference values obtained through manual measurements. The validation experiment also analyzes the uncertainties of the parameters. Results show that the algorithm can reliably estimate the number (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>MPE</mi><mo>=</mo><mo>−</mo><mn>5</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>σ</mi><mo>=</mo><mn>6</mn><mo>%</mo></mrow></semantics></math></inline-formula>) and the radius of the visible portion of the grape clusters (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>MPE</mi><mo>=</mo><mn>0.8</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>σ</mi><mo>=</mo><mn>7</mn><mo>%</mo></mrow></semantics></math></inline-formula>). Instead, the volume estimated in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>px</mi><mn>3</mn></msup></semantics></math></inline-formula> results in a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>MPE</mi><mo>=</mo><mn>0.4</mn><mo>%</mo></mrow></semantics></math></inline-formula> with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>σ</mi><mo>=</mo><mn>21</mn><mo>%</mo></mrow></semantics></math></inline-formula>, thus the corresponding volume in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>mm</mi><mn>3</mn></msup></semantics></math></inline-formula> is affected by high uncertainty. This analysis highlighted that half of the total uncertainty on the volume is due to the camera–object distance <i>d</i> and parameter <i>R</i> used to take into account the proportion of visible grapes with respect to the total grapes in the grape cluster. This issue is mostly due to the absence of a reliable depth measure between the camera and the grapes, which could be overcome by using depth sensors in combination with color images. Despite being preliminary, the results prove that the model and the metrological analysis are a remarkable advancement toward a reliable approach for directly estimating yield from 2D pictures in the field.
format Article
id doaj-art-b9e9c1f6fc704bd58c5a128d4f1d3e45
institution OA Journals
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-b9e9c1f6fc704bd58c5a128d4f1d3e452025-08-20T02:27:39ZengMDPI AGSensors1424-82202024-11-012422730510.3390/s24227305A Stride Toward Wine Yield Estimation from Images: Metrological Validation of Grape Berry Number, Radius, and Volume EstimationBernardo Lanza0Davide Botturi1Alessandro Gnutti2Matteo Lancini3Cristina Nuzzi4Simone Pasinetti5Department of Mechanical and Industrial Engineering (DIMI), University of Brescia, Via Branze 38, 25123 Brescia, ItalyDepartment of Mechanical and Industrial Engineering (DIMI), University of Brescia, Via Branze 38, 25123 Brescia, ItalyDepartment of Information Engineering (DII), University of Brescia, Via Branze 38, 25123 Brescia, ItalyDepartment of Medical and Surgical Specialties, Radiological Sciences, and Public Health (DSMC), University of Brescia, Viale Europa 11, 25123 Brescia, ItalyDepartment of Mechanical and Industrial Engineering (DIMI), University of Brescia, Via Branze 38, 25123 Brescia, ItalyDepartment of Mechanical and Industrial Engineering (DIMI), University of Brescia, Via Branze 38, 25123 Brescia, ItalyYield estimation is a key point theme for precision agriculture, especially for small fruits and in-field scenarios. This paper focuses on the metrological validation of a novel deep-learning model that robustly estimates both the number and the radii of grape berries in vineyards using color images, allowing the computation of the visible (and total) volume of grape clusters, which is necessary to reach the ultimate goal of estimating yield production. The proposed algorithm is validated by analyzing its performance on a custom dataset. The number of berries, their mean radius, and the grape cluster volume are converted to millimeters and compared to reference values obtained through manual measurements. The validation experiment also analyzes the uncertainties of the parameters. Results show that the algorithm can reliably estimate the number (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>MPE</mi><mo>=</mo><mo>−</mo><mn>5</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>σ</mi><mo>=</mo><mn>6</mn><mo>%</mo></mrow></semantics></math></inline-formula>) and the radius of the visible portion of the grape clusters (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>MPE</mi><mo>=</mo><mn>0.8</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>σ</mi><mo>=</mo><mn>7</mn><mo>%</mo></mrow></semantics></math></inline-formula>). Instead, the volume estimated in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>px</mi><mn>3</mn></msup></semantics></math></inline-formula> results in a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>MPE</mi><mo>=</mo><mn>0.4</mn><mo>%</mo></mrow></semantics></math></inline-formula> with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>σ</mi><mo>=</mo><mn>21</mn><mo>%</mo></mrow></semantics></math></inline-formula>, thus the corresponding volume in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>mm</mi><mn>3</mn></msup></semantics></math></inline-formula> is affected by high uncertainty. This analysis highlighted that half of the total uncertainty on the volume is due to the camera–object distance <i>d</i> and parameter <i>R</i> used to take into account the proportion of visible grapes with respect to the total grapes in the grape cluster. This issue is mostly due to the absence of a reliable depth measure between the camera and the grapes, which could be overcome by using depth sensors in combination with color images. Despite being preliminary, the results prove that the model and the metrological analysis are a remarkable advancement toward a reliable approach for directly estimating yield from 2D pictures in the field.https://www.mdpi.com/1424-8220/24/22/7305measurement sciencemachine visionviticulturedeep learningfruit countingfruit size estimation
spellingShingle Bernardo Lanza
Davide Botturi
Alessandro Gnutti
Matteo Lancini
Cristina Nuzzi
Simone Pasinetti
A Stride Toward Wine Yield Estimation from Images: Metrological Validation of Grape Berry Number, Radius, and Volume Estimation
Sensors
measurement science
machine vision
viticulture
deep learning
fruit counting
fruit size estimation
title A Stride Toward Wine Yield Estimation from Images: Metrological Validation of Grape Berry Number, Radius, and Volume Estimation
title_full A Stride Toward Wine Yield Estimation from Images: Metrological Validation of Grape Berry Number, Radius, and Volume Estimation
title_fullStr A Stride Toward Wine Yield Estimation from Images: Metrological Validation of Grape Berry Number, Radius, and Volume Estimation
title_full_unstemmed A Stride Toward Wine Yield Estimation from Images: Metrological Validation of Grape Berry Number, Radius, and Volume Estimation
title_short A Stride Toward Wine Yield Estimation from Images: Metrological Validation of Grape Berry Number, Radius, and Volume Estimation
title_sort stride toward wine yield estimation from images metrological validation of grape berry number radius and volume estimation
topic measurement science
machine vision
viticulture
deep learning
fruit counting
fruit size estimation
url https://www.mdpi.com/1424-8220/24/22/7305
work_keys_str_mv AT bernardolanza astridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT davidebotturi astridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT alessandrognutti astridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT matteolancini astridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT cristinanuzzi astridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT simonepasinetti astridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT bernardolanza stridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT davidebotturi stridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT alessandrognutti stridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT matteolancini stridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT cristinanuzzi stridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation
AT simonepasinetti stridetowardwineyieldestimationfromimagesmetrologicalvalidationofgrapeberrynumberradiusandvolumeestimation